Introduces circulate-firing neurons, time-step-wise learnable surrogate gradients, and balanced loss for direct SNN training, reporting competitive results on datasets and Transformers.
Lm-ht snn: Enhancing the performance of snn to ann counterpart through learnable multi-hierarchical threshold model,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradients
Introduces circulate-firing neurons, time-step-wise learnable surrogate gradients, and balanced loss for direct SNN training, reporting competitive results on datasets and Transformers.